diff options
author | Chris Dyer <cdyer@cs.cmu.edu> | 2011-12-29 21:08:30 -0500 |
---|---|---|
committer | Chris Dyer <cdyer@cs.cmu.edu> | 2011-12-29 21:08:30 -0500 |
commit | aac3ef3e3fdf636406fc61a40096cee6381e5461 (patch) | |
tree | e014b029915614a23a8b2691a37fa14204a84a89 /gi/pf/base_measures.h | |
parent | c96125ad4860aa823ff2f17aa3ccb565c8f99c0e (diff) |
lexical alignment samplers
Diffstat (limited to 'gi/pf/base_measures.h')
-rw-r--r-- | gi/pf/base_measures.h | 50 |
1 files changed, 48 insertions, 2 deletions
diff --git a/gi/pf/base_measures.h b/gi/pf/base_measures.h index 7ce7e2e6..fbd1c3ad 100644 --- a/gi/pf/base_measures.h +++ b/gi/pf/base_measures.h @@ -7,6 +7,7 @@ #include <cmath> #include <iostream> +#include "unigrams.h" #include "trule.h" #include "prob.h" #include "tdict.h" @@ -49,6 +50,51 @@ struct Model1 { std::vector<std::map<WordID, prob_t> > ttable; }; +struct CompletelyUniformBase { + explicit CompletelyUniformBase(const unsigned ves) : kUNIFORM(1.0 / ves) {} + prob_t operator()(const TRule&) const { + return kUNIFORM; + } + const prob_t kUNIFORM; +}; + +struct UnigramWordBase { + explicit UnigramWordBase(const std::string& fname) : un(fname) {} + prob_t operator()(const TRule& r) const { + return un(r.e_); + } + const UnigramWordModel un; +}; + +struct PhraseConditionalUninformativeBase { + explicit PhraseConditionalUninformativeBase(const unsigned vocab_e_size) : + kUNIFORM_TARGET(1.0 / vocab_e_size) { + assert(vocab_e_size > 0); + } + + // return p0 of rule.e_ | rule.f_ + prob_t operator()(const TRule& rule) const { + return p0(rule.f_, rule.e_, 0, 0); + } + + prob_t p0(const std::vector<WordID>& vsrc, const std::vector<WordID>& vtrg, int start_src, int start_trg) const; + + const prob_t kUNIFORM_TARGET; +}; + +struct PhraseConditionalUninformativeUnigramBase { + explicit PhraseConditionalUninformativeUnigramBase(const std::string& file, const unsigned vocab_e_size) : u(file, vocab_e_size) {} + + // return p0 of rule.e_ | rule.f_ + prob_t operator()(const TRule& rule) const { + return p0(rule.f_, rule.e_, 0, 0); + } + + prob_t p0(const std::vector<WordID>& vsrc, const std::vector<WordID>& vtrg, int start_src, int start_trg) const; + + const UnigramModel u; +}; + struct PhraseConditionalBase { explicit PhraseConditionalBase(const Model1& m1, const double m1mixture, const unsigned vocab_e_size) : model1(m1), @@ -83,7 +129,7 @@ struct PhraseJointBase { assert(vocab_e_size > 0); } - // return p0 of rule.e_ | rule.f_ + // return p0 of rule.e_ , rule.f_ prob_t operator()(const TRule& rule) const { return p0(rule.f_, rule.e_, 0, 0); } @@ -113,7 +159,7 @@ struct PhraseJointBase_BiDir { assert(vocab_e_size > 0); } - // return p0 of rule.e_ | rule.f_ + // return p0 of rule.e_ , rule.f_ prob_t operator()(const TRule& rule) const { return p0(rule.f_, rule.e_, 0, 0); } |